{
  "id": 19175,
  "url": "https://arxiv.org/abs/2608.13255v1",
  "title": "GeoCache: Training-Free Acceleration of Multi-View Texture Diffusion via Geometric Delta Transport",
  "summary": "Geometry-conditioned multi-view diffusion enables high-quality 3D texture generation, but its repeated per-view denoiser evaluations introduce substantial computational cost. Existing training-free accelerators primarily exploit temporal redundancy by reusing computation across denoising steps. In multi-view texturing, however, skipping a step also removes the cross-view interaction that continually aligns different observations of the same surface, leading to rapidly degraded consistency and fi",
  "authors": "Haotang Li, Zhenyu Qi, Shaohan Henry Wang, Kebin Peng, Yutong Zhao, Zi Wang et al.",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T13:57:35.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19175",
  "original_url": "https://arxiv.org/abs/2608.13255v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}